Image defogging method, image defogging system and computer readable storage medium

Abstract

The invention provides an image defogging method, an image defogging system and a computer readable storage medium. The method comprises the following steps: obtaining a foggy image I(x); preliminarily estimating an atmospheric light value A0 by adopting a quadtree search method; correcting the atmospheric light value A0 according to a self-adaptive atmospheric light correction method to obtain acorrected atmospheric light value A; calculating a dark channel mean value of the foggy image I(x); estimating a projection rate tM(x) according to the dark channel mean value; performing adaptive compensation on the projection rate tM(x) to obtain a compensated transmittance t(x); respectively inputting the corrected atmospheric light value A and the compensated transmissivity t(x) into an imagedefogging model I(x) = J(x)t (x) + (I-t(x))A to obtain a defogged image J(x); and adjusting the image brightness of the defogged image J(x) by adopting an adjustment function to obtain a restored image. According to the method, the problems of halo, color distortion and the like can be effectively avoided, and the restored image is outstanding in detail and has a better visual effect.

Description

technical field [0001] The technical field of image processing of the present invention, in particular, relates to an image defogging method, system and computer-readable storage medium. Background technique [0002] In the monitoring system based on visual image information, the foggy image seriously affects the feature extraction of the target, so that the work of target detection and target tracking cannot be performed. It is of great significance to dehaze the foggy image, which can effectively improve the target detection and tracking accuracy. [0003] At present, image defogging methods are mainly divided into two categories: one is based on image enhancement, and the other is based on physical models. The former includes histogram equalization and Retinex algorithm. This type of method achieves image clarity by improving the contrast of foggy images or highlighting image features, but it is easy to cause loss of image details; the latter studies the scattering of li...

AI Technical Summary

Problems solved by technology

The former includes histogram equalization and Retinex algorithm, which achieve image clarity by improving the contrast of foggy images or highlighting image features, but it is easy to cause image details to be lost; the latter studies the scattering effect of atmospheric suspended particles on light, Establish a physical model of the foggy image, and further invert and restore a clear image

Images